On Fri, 14 Jul 2006, Alfred Perlstein wrote:
Could the KASSERT here be changed to a warning log message instead?
I don't like the idea of kernel modules failing catastrophically
when they could fail gracefully by just emitting an error.
Is that OK?
+ KASSERT(kp.ki_stat <= sizeof(linux_state),
+ ("linprocfs: don't know how to handle unknown FreeBSD state"));
Or, if this is really just a structure size thing, we should pick it up at
compile-time with CTASSERT?
Robert N M Watson
Computer Laboratory
University of Cambridge
-Alfred
* Alexander Leidinger <[EMAIL PROTECTED]> [060708 07:06] wrote:
netchild 2006-07-08 14:06:56 UTC
FreeBSD src repository
Modified files: (Branch: RELENG_6)
sys/fs/pseudofs pseudofs_vnops.c
sys/compat/linux linux_misc.c
sys/compat/linprocfs linprocfs.c
Log:
MFC:
- linux_misc.c 1.179
Don't copyout/do unneccesary work if the buffer is a NULL pointer.
Noticed by: Dmitry Ganenko <[EMAIL PROTECTED]>
Reviewed by: rdivacky (the original version as in emulation@)
- linprocfs.c 1.96:
Improve linprovfs to provide/fix the
- process state (idle, sleeping, running, ...) [1]
- the process group ID of the process which owns the connected tty
- some page fault stats
- time spend in kernel/userland
- priority/nice value
- starttime [1]
- memory/swap stats
- scheduling policy
Additionally add some new fields and correct some not filled out ones.
This brings us down to 15 dummy fields.
The fields marked with [1] are needed to get Oracle 10 running. The
starttime
field is not completely right, since it displays the _same_ starttime for
_every_ process, but at least it is not 0 and Oracle accepts this.
Noticed by: Dmitry Ganenko <[EMAIL PROTECTED]> [1]
Reviewed by: des, rdivacky
- pseudofs_vnops.c 1.60:
Correctly calculate a buffer length. It was off by one so a read() returned
one byte less than needed.
Noticed by: Dmitry Ganenko <[EMAIL PROTECTED]>
Testcase by: Dmitry Ganenko <[EMAIL PROTECTED]>
Reviewed by: des
Submitted by: rdivacky
Sponsored by: Google SoC 2006
All of those are needed for Oracle 10. Since previous Oracle versions work
just fine without those fixes, these patches can be seen as regression fixes
too. Because of this I think they are a RELENG_6_x candidate (MFC reminder
set).
MFC after: 1 month
Revision Changes Path
1.89.2.4 +51 -27 src/sys/compat/linprocfs/linprocfs.c
1.170.2.1 +13 -11 src/sys/compat/linux/linux_misc.c
1.56.2.4 +1 -1 src/sys/fs/pseudofs/pseudofs_vnops.c
--
- Alfred Perlstein
- coder / sysadmin / FreeBSD Hacker / All that jazz -
_______________________________________________
[email protected] mailing list
http://lists.freebsd.org/mailman/listinfo/cvs-all
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
